IP Library Granted Patent US 12,303,233
Granted Patent B2
US 12,303,233 · App. 18/331,108 · Granted May 20, 2025

Devices, systems, and methods for virtual staining

Inventors: Peter Bryant-Greenwood (Honolulu, HI); Kevin P. Rosenblatt (Houston, TX); Jeffrey N. Yu (Honolulu, HI)
Assignee: Genetic Innovations, Inc.
A61B5/0059G06T5/90G06T7/0012G06T7/90A61B5/055A61B2576/00G01R33/5608G06T2207/10024G06T2207/10056G06T2207/30024
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,303,233
App. No.
18/331,108
Granted
May 20, 2025
Kind
B2
Abstract

The disclosure herein provides methods, systems, and devices for virtually staining biological tissue for enhanced visualization without use of an actual dye or tag by detecting how each pixel of an unstained tissue image changes in waveform after staining with a certain dye(s) and/or tag(s) or other transformation under a certain electromagnetic radiation source, developing a virtual staining transform based on such detection, and applying such virtual staining transform to an unstained biological tissue to virtually stain the tissue.

Claims (48)

1. A system for virtually staining a tissue sample, the system comprising:

at least one hardware processor; and

at least one non-transitory memory storing instructions which, when executed by the at least one hardware processor, cause the system to:

access an electronic medical image of the tissue sample, the electronic medical image of the tissue sample comprising a plurality of pixels generated based on electromagnetic radiation detected by a detector, wherein the plurality of pixels comprises a first pixel and a second pixel;

determine that a first waveform signature associated with the first pixel of the plurality of pixels is based on a combination of a first plurality of waveform signatures corresponding to multiple substances in the tissue sample at a location associated with the first pixel;

determine the first plurality of waveform signatures;

apply transformation data to the first plurality of waveform signatures in order to obtain a first plurality of outputs;

determine a first single output pixel by volume averaging the first plurality of outputs;

generate a virtually stained first input image of the tissue sample, wherein the virtually stained first input image comprises at least a first single output pixel;

determine that a second waveform signature associated with the second pixel of the plurality of pixels is based on a combination of a second plurality of waveform signatures corresponding to multiple substances in the tissue sample at a location associated with the second pixel;

determine the second plurality of waveform signatures;

apply transformation data to the second plurality of waveform signatures in order to obtain a second plurality of outputs;

determine a second single output pixel by volume averaging the second plurality of outputs;

generate a virtually stained second input image of the tissue sample, wherein the virtually stained second input image comprises at least a second single output pixel;

generate a combined virtually stained image of the tissue sample comprising the virtually stained first input image and the virtually stained second input image; and

display the combined virtually stained image of the tissue sample, wherein the combined virtually stained image is substantially identical to an image of the tissue sample when the tissue sample is treated with an actual stain that corresponds to a virtual stain defined by a virtual staining transform.

2. The system for virtually staining a tissue sample of claim 1 , wherein the detector is a multi-spectrum detector.

3. The system for virtually staining a tissue sample of claim 1 , wherein the tissue sample is in vitro.

4. The system for virtually staining a tissue sample of claim 1 , wherein the determining based on the combination of the first plurality of waveform signatures corresponding to multiple substances in the tissue sample at the location associated with the first pixel and the determining based on the combination of the second plurality of waveform signatures corresponding to multiple substances in the tissue sample at the location associated with the second pixel is based at least in part on a first identified vector signature associated with the first pixel of the plurality of pixels and a second identified vector signature associated with the second pixel of the plurality of pixels.

5. The system for virtually staining a tissue sample of claim 1 , wherein the tissue sample is a three-dimensional tissue sample.

6. The system for virtually staining a tissue sample of claim 5 , wherein the detector is configured to change a focal depth to obtain two-dimensional electromagnetic radiation data at varying z depths of the three-dimensional tissue sample.

7. The system for virtually staining a tissue sample of claim 1 , wherein the detector is incorporated into a medical probe.

8. The system for virtually staining a tissue sample of claim 1 , wherein the actual stain is a dye configured to color certain portions of the tissue sample.

9. The system for virtually staining a tissue sample of claim 1 , wherein the actual stain is a tag.

10. The system for virtually staining a tissue sample of claim 9 , wherein the tag is at least one of an antibody, an aptamer, or a fluorescent protein.

11. A method for virtually staining a tissue sample, the method comprising:

accessing an electronic medical image of the tissue sample, the electronic medical image of the tissue sample comprising a plurality of pixels generated based on electromagnetic radiation detected by a detector, wherein the plurality of pixels comprises a first pixel and a second pixel;

determining that a first waveform signature associated with the first pixel of the plurality of pixels is based on a combination of a first plurality of waveform signatures corresponding to multiple substances in the tissue sample at a location associated with the first pixel;

determining the first plurality of waveform signatures;

applying transformation data to the first plurality of waveform signatures in order to obtain a first plurality of outputs;

determining a first single output pixel by volume averaging the first plurality of outputs;

generating a virtually stained first input image of the tissue sample, wherein the virtually stained first input image comprises at least the first single output pixel;

determining that a second waveform signature associated with the second pixel of the plurality of pixels is based on a combination of a second plurality of waveform signatures corresponding to multiple substances in the tissue sample at a location associated with the second pixel;

determining the second plurality of waveform signatures;

applying transformation data to the second plurality of waveform signatures in order to obtain a second plurality of outputs;

determining a second single output pixel by volume averaging the second plurality of outputs;

generating a virtually stained second input image of the tissue sample, wherein the virtually stained second input image comprises at least the second single output pixel;

generating a combined virtually stained image of the tissue sample comprising the virtually stained first input image and the virtually stained second input image; and

displaying the combined virtually stained image of the tissue sample, wherein the combined virtually stained image is substantially identical to an image of the tissue sample when the tissue sample is treated with an actual stain that corresponds to a virtual stain defined by a virtual staining transform.

12. The method of claim 11 , wherein the detector is a multi-spectrum detector.

13. The method of claim 11 , wherein the tissue sample is in vitro.

14. The method of claim 11 , wherein the determining based on the combination of the first plurality of waveform signatures corresponding to multiple substances in the tissue sample at the location associated with the first pixel and the determining based on the combination of the second plurality of waveform signatures corresponding to multiple substances in the tissue sample at the location associated with the second pixel is based at least in part on a first identified vector signature associated the first pixel of the plurality of pixels and a second identified vector signature associated with the second pixel of the plurality of pixels.

15. The method of claim 11 , wherein the tissue sample is a three-dimensional tissue sample.

16. The method of claim 15 , wherein the detector is configured to change a focal depth to obtain two-dimensional electromagnetic radiation data at varying z depths of the three-dimensional tissue sample.

17. The method of claim 11 , wherein the detector is incorporated into a medical probe.

18. The method of claim 11 , wherein the actual stain is at least one of a dye configured to color certain portions of the tissue sample.

19. The method of claim 11 , wherein the actual stain is a tag.

20. The method of claim 19 , wherein the tag is at least one of an antibody, an aptamer, or a fluorescent protein.

Assignments (2)
CHANGE OF NAME Recorded Aug 14, 2025
From: GENETIC INNOVATIONS, INC.
To: PATHSCIENCE, INC.
Reel/Frame 072460/0584 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 7, 2023
From: BRYANT-GREENWOOD, PETER; ROSENBLATT, KEVIN P.; YU, JEFFREY N.
To: GENETIC INNOVATIONS, INC.
Reel/Frame 063888/0313 →
Continuity (6)
Continuation 16911098 · Jun 24, 2020
Continuation 14224903 · Mar 25, 2014
Continuation 13843588 · Mar 15, 2013
Provisional Application 61656930 · Jun 7, 2012
Provisional Application 61612925 · Mar 19, 2012
Related Publication 20230404406A1 · Dec 21, 2023
References Cited (48)
US 5991028A · Cabib et al. · 1999 [cited by applicant]
US 6160618A · Garner · 2000 [cited by applicant]
US 6198532B1 · Cabib et al. · 2001 [cited by applicant]
US 6337472B1 · Garner et al. · 2002 [cited by applicant]
US 7945077B2 · Demos · 2011 [cited by applicant]
US 8320996B2 · Panasyuk et al. · 2012 [cited by applicant]
US 8705833B2 · Yag et al. · 2014 [cited by applicant]
US 8725237B2 · Bryant-Greenwood · 2014 [cited by applicant]
US 8977017B2 · Otsuka et al. · 2015 [cited by applicant]
US 10729325B2 · Bryant-Greenwood · 2020 [cited by examiner]
US 11684264B2 · Bryant-Greenwood · 2023 [cited by examiner]
US 20010017938A1 · Kerschmann et al. · 2001 [cited by applicant]
US 20030118222A1 · Foran et al. · 2003 [cited by applicant]
US 20040085443A1 · Kallioniemi et al. · 2004 [cited by applicant]
US 20080082458A1 · Airoldi et al. · 2008 [cited by applicant]
US 20080102487A1 · Yao et al. · 2008 [cited by applicant]
US 20080273788A1 · Soenksen et al. · 2008 [cited by applicant]
US 20090245610A1 · Can et al. · 2009 [cited by applicant]
US 20100056928A1 · Zuzak et al. · 2010 [cited by applicant]
US 20100128988A1 · Kincaid · 2010 [cited by applicant]
US 20100195903A1 · Tani · 2010 [cited by applicant]
US 20110074944A1 · Can et al. · 2011 [cited by applicant]
US 20110109735A1 · Otsuka · 2011 [cited by applicant]
US 20120147002A1 · Young et al. · 2012 [cited by applicant]
US 20120269417A1 · Young et al. · 2012 [cited by applicant]
US 20130071002A1 · Otsuka · 2013 [cited by applicant]
US 20130317369A1 · Bryant-Greenwood · 2013 [cited by applicant]
US 20140021813A1 · Bryant-Greenwood et al. · 2014 [cited by applicant]
US 20140252200A1 · Garsha et al. · 2014 [cited by applicant]
WO WO2006091221 · 2006 [cited by applicant]
WO WO2010061319 · 2010 [cited by applicant]
WO WO2011163624 · 2011 [cited by applicant]
WO WO2013142366 · 2013 [cited by applicant]
WO WO2019046774 · 2019 [cited by applicant]
Ferris, Daron G. et al., “Multimodal Hyperspectral Imaging for the Noninvasive Diagnosis of Cervical Neoplasia,” J. of Lower Gential Tract Disease, vol. 5, No. 2, 2001, pp. 65-72. [cited by applicant]
Folkman, Mark et al., “EO-1/Hyperion Hyperspectral Imager Design, Development, Characterization, and Calibration,” SPIE, vol. 4151, 2000, 12 pages. [cited by applicant]
Geho, David et al., “Pegylated, Steptavidin-Conjugated Quantum Dots are EffectiveDetection Elements for Reverse-Phase Protein Microarrays,” Bioconjugate Chem. Vol. 16, No. 3, 2005, pp. 559-566. [cited by applicant]
Huebschman, Michael L. et al., “Hyperspectral Microscopy Imaging to AnalyzePathology Samples with Multi-colors Reduces Time and Cost,” Proc. SPIE vol. 7182, 71821F, 2009, 10 pages. [cited by applicant]
Bautista, et al., “Digital simulation of staining in histopathology multispectral images:enhancement and linear transformation of spectral transmittance,” Journal of Biomedical Optics, 17(5), 056013 (May 2012). [cited by applicant]
Bautista, et al., “Digital Staining of Unstained Pathological Tissue Samples through Spectral Transmittance Classification,” Optical Review, vol. 12, No. 1 (2005) pp. 1-8. [cited by applicant]
Bautista, et al., “Digital Staining for Histopathology Multispectral Images by the Combined Application of Spectral Enhancement and Spectral Transformation,” 33rd Annual International Conference of the IEEE EMBS, Aug. 3… [cited by applicant]
Extended European Search Report in EP 13764197.3 dated Dec. 19, 2014 in 11 pages. [cited by applicant]
International Search Report and Written Opinion of the International Search Authority in PCT/US2013/032389, dated Jul. 8, 2013, 13 pages. [cited by applicant]
Memarsadeghi, Nargess et al., “NASA Computational Case Study, Hyperspectral DataProcessing: Cryospheric Change Detection,” Computing in Science and Engineering, vol. 14, No. 4, 2012, pp. 92-97, 11 pages. [cited by applicant]
Shippert, Peg, “Introduction to Hyperspectral Image Analysis,” Online J. of Space Commun, Issue 3, 2003, 13 pages. [cited by applicant]
International Search Report and Written Opinion of the International Search Authority in PCT/US2018/049185, dated Nov. 2, 2018, 4 pages. [cited by applicant]
Bautista, Pinky et al., “Digital simulation of staining in histopathology multispectral images:enhancement and linear transformation of spectral transmittance,”vol. 17, No. 5, 2012, pp. 1-11. [cited by applicant]
Bai et al., “Label-free virtual HER2 immunohistochemical staining of breast tissue using deep learning,” pp. 1-26. [cited by applicant]
Cited By (1)
US 12,702,303